Fix ClipQuantFusion crash when Clip has multiple input edges #26923
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qti-yuduo
changed the title
Contributor
From AISummaryThis PR fixes a runtime exception in the Key Changes
Review AnalysisCorrectness
Performance
ConclusionThis is a straightforward and correct bug fix. The inclusion of a regression test gives high confidence in the solution. LGTM. |
Member
|
/azp run Linux QNN CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 4 pipeline(s). |
adrianlizarraga
approved these changes
Jan 14, 2026
Contributor
adrianlizarraga
left a comment
adrianlizarraga
left a comment
There was a problem hiding this comment.
looks good to me
edgchen1
approved these changes
Jan 15, 2026
Contributor
|
hm, there appears to be an invisible unresolved comment that's blocking the merge |
Contributor
|
can't figure out how to merge this one. replacing with #27016. |
yuslepukhin
pushed a commit
that referenced
this pull request
Jan 16, 2026
## Motivation `ClipQuantFusion in clip_quantizelinear.cc` calls `graph_utils::RemoveNode()` without first checking `graph_utils::CanRemoveNode()`. When a Clip node has min/max inputs from DequantizeLinear nodes (instead of initializers), it has multiple input edges. `RemoveNode()` throws exception: ``` [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: graph_utils.cc:650 bool onnxruntime::graph_utils::RemoveNode(onnxruntime::Graph&, onnxruntime::Node&) Should be unreachable if CanRemoveNodeAndMergeEdges is in sync with the logic here. ``` ## Fix: Added `CanRemoveNode()` check to `ClipQuantFusion::SatisfyCondition()` to skip nodes that cannot be safely removed. ## Test: Added `ClipQuantFusion_MultipleInputEdges` test that creates a Clip node with min from a DQ node (2 input edges) and verifies the optimizer doesn't crash. ## Note: This PR is a duplicate of #26923 which GitHub is preventing us from merging. Credit goes to original author @qti-yuduo. --------- Co-authored-by: Yuduo Wu <yuduow@qti.qualcomm.com>
alex-spacemit
pushed a commit
to spacemit-com/onnxruntime
that referenced
this pull request
Jan 20, 2026
…ft#27016) ## Motivation `ClipQuantFusion in clip_quantizelinear.cc` calls `graph_utils::RemoveNode()` without first checking `graph_utils::CanRemoveNode()`. When a Clip node has min/max inputs from DequantizeLinear nodes (instead of initializers), it has multiple input edges. `RemoveNode()` throws exception: ``` [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: graph_utils.cc:650 bool onnxruntime::graph_utils::RemoveNode(onnxruntime::Graph&, onnxruntime::Node&) Should be unreachable if CanRemoveNodeAndMergeEdges is in sync with the logic here. ``` ## Fix: Added `CanRemoveNode()` check to `ClipQuantFusion::SatisfyCondition()` to skip nodes that cannot be safely removed. ## Test: Added `ClipQuantFusion_MultipleInputEdges` test that creates a Clip node with min from a DQ node (2 input edges) and verifies the optimizer doesn't crash. ## Note: This PR is a duplicate of microsoft#26923 which GitHub is preventing us from merging. Credit goes to original author @qti-yuduo. --------- Co-authored-by: Yuduo Wu <yuduow@qti.qualcomm.com>
tianleiwu
pushed a commit
that referenced
this pull request
Jan 21, 2026
## Motivation `ClipQuantFusion in clip_quantizelinear.cc` calls `graph_utils::RemoveNode()` without first checking `graph_utils::CanRemoveNode()`. When a Clip node has min/max inputs from DequantizeLinear nodes (instead of initializers), it has multiple input edges. `RemoveNode()` throws exception: ``` [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Exception during initialization: graph_utils.cc:650 bool onnxruntime::graph_utils::RemoveNode(onnxruntime::Graph&, onnxruntime::Node&) Should be unreachable if CanRemoveNodeAndMergeEdges is in sync with the logic here. ``` ## Fix: Added `CanRemoveNode()` check to `ClipQuantFusion::SatisfyCondition()` to skip nodes that cannot be safely removed. ## Test: Added `ClipQuantFusion_MultipleInputEdges` test that creates a Clip node with min from a DQ node (2 input edges) and verifies the optimizer doesn't crash. ## Note: This PR is a duplicate of #26923 which GitHub is preventing us from merging. Credit goes to original author @qti-yuduo. --------- Co-authored-by: Yuduo Wu <yuduow@qti.qualcomm.com> (cherry picked from commit cc2b01b)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Motivation
ClipQuantFusion in clip_quantizelinear.cccallsgraph_utils::RemoveNode()without first checkinggraph_utils::CanRemoveNode(). When a Clip node has min/max inputs from DequantizeLinear nodes (instead of initializers), it has multiple input edges.RemoveNode()throws exception:Fix:
Added
CanRemoveNode()check toClipQuantFusion::SatisfyCondition()to skip nodes that cannot be safely removed.Test:
Added
ClipQuantFusion_MultipleInputEdgestest that creates a Clip node with min from a DQ node (2 input edges) and verifies the optimizer doesn't crash.